Reranking Machine Translation Hypotheses with Structured and Web-based Language Models

04/25/2021
by   Wen Wang, et al.
12

In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from Constraint Dependency Grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic dependency constraints. Two structured language models are applied for N-best rescoring, one is an almost-parsing language model, and the other utilizes more syntactic features by explicitly modeling syntactic dependencies between words. We also investigate effective and efficient language modeling methods to use N-grams extracted from up to 1 teraword of web documents. We apply all these language models for N-best re-ranking on the NIST and DARPA GALE program 2006 and 2007 machine translation evaluation tasks and find that the combination of these language models increases the BLEU score up to 1.6 test sets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2015

Polish - English Speech Statistical Machine Translation Systems for the IWSLT 2013

This research explores the effects of various training settings from Pol...
research
09/30/2015

Polish to English Statistical Machine Translation

This research explores the effects of various training settings on a Pol...
research
09/29/2015

Polish - English Speech Statistical Machine Translation Systems for the IWSLT 2014

This research explores effects of various training settings between Poli...
research
03/07/2017

Data Noising as Smoothing in Neural Network Language Models

Data noising is an effective technique for regularizing neural network m...
research
06/13/2023

Tokenization with Factorized Subword Encoding

In recent years, language models have become increasingly larger and mor...
research
04/18/2021

Linguistic dependencies and statistical dependence

What is the relationship between linguistic dependencies and statistical...
research
08/27/2022

On Unsupervised Training of Link Grammar Based Language Models

In this short note we explore what is needed for the unsupervised traini...

Please sign up or login with your details

Forgot password? Click here to reset